Submitted by Zuyan 23 ViQ: Text-Aligned Visual Quantized Representations at Any Resolution Tencent Hunyuan 3 1
Submitted by Jinyang23 15 OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning · 11 authors 5 1
Submitted by taesiri 15 Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation Qwen
Submitted by jinzhuoran 5 Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It Chinese Academic of Science Institute of Automation 0 1
Submitted by jaehong31 4 Confidence-Aware Tool Orchestration for Robust Video Understanding Nanyang Technological University Singapore 1 1
Submitted by rebeccazzzz 4 GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents · 7 authors 1 1
Submitted by nicklashansen - Hallucination in World Models is Predictable and Preventable University of California at San Diego 1
Submitted by taesiri - COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami GoogleDeepMind
taesiri 
